Meta tags:
Headings (most frequently used words):
selected, experiences, biography, news, product, release, industrial, research, publications, full, list, indicates, equal, contribution, working, internship, invited, talks, professional, services, honors, awards, teaching, experience,
Text of the page (most frequently used words):
2024 (31), 2025 (28), liu (26), #research (23), and (21), generation (20), accepted (19), with (18), cosmos (17), video (16), 2023 (16), paper (16), 2022 (14), models (14), top (13), foundation (13), github (13), xian (13), world (11), nvidia (11), cvpr (10), team (10), image (10), model (10), one (10), nbsp (10), for (9), eccv (9), technical (9), project (9), 2021 (8), best (8), human (8), release (8), multi (7), the (7), intern (7), core (7), contributor (7), grok (7), imagine (7), iclr (6), conference (6), modal (6), xai (6), demo (6), papers (6), are (6), scholarship (5), 2020 (5), award (5), university (5), neurips (5), driven (5), visual (5), supervisor (5), group (5), vision (5), ziwei (5), huggingface (5), report (5), contributions (5), open (5), training (5), see (5), you (5), outstanding (4), reviewer (4), ces (4), aaai (4), neural (4), audio (4), hyperhuman (4), zhou (4), dec (4), omni (4), member (4), staff (4), computer (4), xihui (4), lin (4), code (4), webpage (4), post (4), two (4), 2019 (3), sensetime (3), zhejiang (3), hong (3), kong (3), overall (3), iccv (3), time (3), hyper (3), realistic (3), towards (3), from (3), modeling (3), qianyi (3), jun (3), wayne (3), hang (3), sergey (3), tulyakov (3), snap (3), david (3), ming (3), internship (3), scientist (3), working (3), recognition (3), processing (3), dahua (3), oral (3), arxiv (3), humangaussian (3), blog (3), tokenizers (3), improved (3), physical (3), released (3), our (3), sourced (3), engg (2), discrete (2), engineers (2), fall (2), spring (2), tang (2), program (2), bachelor (2), travel (2), cnet (2), selected (2), awards (2), siggraph (2), icml (2), semantic (2), aware (2), implicit (2), portrait (2), speech (2), gesture (2), latent (2), structural (2), diffusion (2), jian (2), ren (2), sept (2), ying (2), shan (2), xiaohang (2), zhan (2), laboratory (2), lindell (2), sherwin (2), bahmani (2), mar (2), wang (2), deep (2), imagination (2), generative (2), experiences (2), european (2), park (2), ivan (2), skorokhodov (2), text (2), ieee (2), cvf (2), pattern (2), spotlight (2), long (2), review (2), score (2), rank (2), highlight (2), full (2), adaptive (2), control (2), data (2), pipelines (2), source (2), transfer (2), benchmark (2), tokenizer (2), suite (2), pre (2), platform (2), api (2), doc (2), arena (2), start (2), quality (2), available (2), will (2), santa (2), clara (2), seattle (2), join (2), stay (2), tuned (2), 2026 (2), ranking (2), degree (2), 2440, mathematics, 1120, linear, algebra, teaching, experience, first, class, academic, excellence, lixin, ucla, csst, thesis, graduate, province, fellowship, scheme, hkpfs, national, honors, journal, tpami, ijcv, tvcg, tip, tmm, cgf, wacv, asia, acl, aistats, acm, area, chair, senior, committee, professional, services, techbeat, nanjing, invited, talks, dai, intelligent, aug, shanghai, lab, digital, content, jul, feb, creative, may, tencent, host, uoft, toronto, computational, imaging, visiting, student, ting, chun, pretrain, now, andrea, tagliasacchi, gordon, wetzstein, jeong, joon, victor, rong, yifan, tc4d, trajectory, conditioned, romero, christopher, daniel, tsung, hermann, kumbong, hmar, efficient, hierarchical, masked, autoregressive, advances, information, systems, yuanqi, bolei, yinghao, 10min, short, 3min, openreview, international, learning, representations, yanyu, aliaksandr, siarohin, gang, zeng, jiaxiang, gaussian, splatting, publications, indicates, equal, contribution, list, repo, multimodal, continuous, captioning, evaluation, simulation, keynote, jensen, huang, auto, regressive, industrial, blogpost, product, show, more, three, ssp, nerf, angie, tmlr, los, angeles, collaborated, high, framework, all, menlo, genai, meta, receiving, building, large, scale, honored, receive, great, thanks, sota, four, won, controllability, transfer1, predict2, pass, defense, become, officially, presentation, version, check, lmarena, news, pretraining, before, that, was, obtained, chinese, cuhk, media, mmlab, interest, lies, focus, leading, also, series, ensemble, their, trained, variants, biography, linkedin, twitter, google, scholar, mail, homepage,
Text of the page (random words):
xian liu s homepage xian liu member of technical staff xai seattle wa e mail nbsp nbsp cv nbsp nbsp google scholar nbsp nbsp github nbsp nbsp twitter nbsp nbsp linkedin biography i am a member of technical staff at xai grok imagine team working on the omni model pretraining and visual generation before that i was a research scientist at nvidia research cosmos team i obtained bachelor s degree at zhejiang university in 2021 and ph d degree at the chinese university of hong kong cuhk multi media laboratory mmlab in 2025 my research interest lies in multi modal ai and foundation generative models with focus on omni model pre training and post training i am the core contributor to xai grok imagine a leading image and video generation model i am also core contributor to nvidia cosmos series an ensemble of open source world foundation models and their post trained variants news 02 2026 grok imagine v1 0 is released on lmarena with image ranking top 3 and video ranking top 1 01 2026 grok imagine v1 0 image and video generation released 12 2025 join xai as member of technical staff working on omni and visual generation models stay tuned for our release 11 2025 we release cosmos 2 5 an improved version of world foundation model check our github and technical report 09 2025 one paper is accepted to neurips 2025 07 2025 one paper is accepted to iccv 2025 with oral presentation 06 2025 pass my ph d defense and become dr liu officially 06 2025 we release cosmos predict2 a world foundation model with improved quality models open sourced on github and hf 03 2025 we release cosmos transfer1 a world model with multi modal controllability models open sourced on github and hf 02 2025 two papers are accepted to cvpr 2025 01 2025 cosmos won the best of ces best of ai and best overall awards in cnet 2025 01 2025 we release cosmos a world foundation model platform for physical ai models open sourced on github and hf 01 2025 four papers are accepted to iclr 2025 12 2024 one paper is accepted to aaai 2025 11 2024 we release cosmos tokenizer a suite of sota image video tokenizers with models available on github and hf 09 2024 honored to receive eccv 2024 outstanding reviewer award great thanks for the recognition 07 2024 two papers are accepted to eccv 2024 06 2024 join nvidia research as full time research scientist building large scale foundation models stay tuned for our release 05 2024 one paper is accepted to icml 2024 03 2024 start my internship at nvidia research see you in santa clara 03 2024 two papers are accepted to cvpr 2024 with humangaussian accepted as highlight top 2 8 see you in seattle 01 2024 one paper is accepted to iclr 2024 with hyperhuman receiving review score of 6 6 8 10 top 1 6 rank 01 2024 i will intern at genai team meta ai research in 2024 fall see you in menlo park 11 2023 i will intern at deep imagination research nvidia research in 2024 spring with ming yu liu see you in santa clara 11 2023 a high quality 3d human generation framework humangaussian is released with all the code and models available 10 2023 a hyper realistic human generation foundation model hyperhuman collaborated with snap research is on arxiv 07 2023 one paper is accepted to iccv 2023 05 2023 start my internship at snap research see you in los angeles 03 2023 two papers are accepted to cvpr 2023 03 2023 one paper is accepted to tmlr 2023 09 2022 one paper is accepted to neurips 2022 with angie accepted as spotlight top 5 07 2022 three papers are accepted to eccv 2022 with ssp nerf accepted as oral top 2 7 03 2022 one paper is accepted to cvpr 2022 12 2021 one paper is accepted to aaai 2022 show more product release grok imagine 1 0 xai grok imagine team xian liu core contributor contributions grok imagine image blogpost image arena top 3 video arena top 1 image api doc video api doc industrial research cosmos world foundation model platform for physical ai nvidia cosmos team xian liu core contributor contributions auto regressive foundation model pre training post training ces 25 best of ai best overall webpage project technical report blog github huggingface demo keynote jensen huang ces 25 cosmos 2 5 improved world simulation with video foundation models for physical ai nvidia cosmos team xian liu core contributor contributions data processing pipelines captioning long video generation evaluation transfer post training webpage project technical report blog github huggingface benchmark cosmos tokenizer a suite of image and video neural tokenizers nvidia cosmos team xian liu core contributor contributions continuous discrete image video tokenizers webpage technical report blog github huggingface demo benchmark cosmos transfer world generation with adaptive multimodal control nvidia cosmos team xian liu core contributor contributions adaptive multi modal control data processing pipelines open source repo webpage project technical report demo github huggingface selected publications full list indicates equal contribution humangaussian text driven 3d human generation with gaussian splatting xian liu xiaohang zhan jiaxiang tang ying shan gang zeng dahua lin xihui liu ziwei liu ieee cvf conference on computer vision and pattern recognition cvpr 2024 highlight top 2 8 cvpr 2024 project paper arxiv demo video code models hyperhuman hyper realistic human generation with latent structural diffusion xian liu jian ren aliaksandr siarohin ivan skorokhodov yanyu li dahua lin xihui liu ziwei liu sergey tulyakov international conference on learning representations iclr 2024 review score 6 6 8 10 top 1 6 rank iclr 2024 openreview project paper arxiv short demo 3min long demo 10min github semantic aware implicit neural audio driven video portrait generation xian liu yinghao xu qianyi wu hang zhou wayne wu bolei zhou european conference on computer vision eccv 2022 oral top 2 7 eccv 2022 paper project code audio driven co speech gesture video generation xian liu qianyi wu hang zhou yuanqi du wayne wu dahua lin ziwei liu advances in neural information processing systems neurips 2022 spotlight top 5 neurips 2022 paper project code hmar efficient hierarchical masked autoregressive image generation hermann kumbong xian liu tsung yi lin xihui liu ziwei liu daniel y fu ming yu liu christopher ré david w romero ieee cvf conference on computer vision and pattern recognition cvpr 2025 cvpr 2025 project paper huggingface github tc4d trajectory conditioned text to 4d generation sherwin bahmani xian liu yifan wang ivan skorokhodov victor rong ziwei liu xihui liu jeong joon park sergey tulyakov gordon wetzstein andrea tagliasacchi david b lindell european conference on computer vision eccv 2024 eccv 2024 project paper github working experiences member of technical staff dec 2025 now xai omni pretrain team research scientist jun 2024 dec 2025 nvidia research cosmos team internship experiences generative ai research intern mar 2024 jun 2024 nvidia research deep imagination group supervisor ting chun wang ming yu liu research visiting student dec 2023 mar 2024 uoft toronto computational imaging group host sherwin bahmani david b lindell research intern sept 2023 dec 2023 tencent ai laboratory supervisor xiaohang zhan ying shan research intern may 2023 sept 2023 snap research creative vision group supervisor jian ren sergey tulyakov research intern jul 2021 feb 2022 shanghai ai lab digital content group supervisor hang zhou wayne wu research intern aug 2020 jun 2021 sensetime research intelligent video group supervisor qianyi wu bo dai invited talks the university of hong kong towards multi modal visual generation from human modeling to world foundation models 2025 nanjing university towards multi modal visual generation from human modeling to world foundation models 2025 sensetime towards multi modal visual generation from human modeling to world foundation models 2025 ai time hyperhuman hyper realistic human generation with latent structural diffusion 2024 ai time audio driven co speech gesture video generation 2023 techbeat semantic aware implicit neural audio driven video portrait generation 2022 professional services area chair senior program committee aaai conference reviewer cvpr eccv iccv wacv siggraph siggraph asia acl neurips icml iclr aistats aaai acm mm journal reviewer tpami ijcv tvcg tip tmm eg cgf pg selected honors awards cnet 2025 best of ces best of ai and best overall 2025 eccv outstanding reviewer award 2024 cvpr travel award 2024 iclr travel award 2024 national scholarship 2019 2020 hong kong ph d fellowship scheme hkpfs 2021 2025 outstanding graduate of zhejiang province 2021 outstanding bachelor thesis award of zhejiang university top 1 2021 ucla csst scholarship program 2020 sensetime scholarship 2020 tang lixin scholarship 2019 first class scholarship for academic excellence 2019 2020 teaching experience engg 1120 linear algebra for engineers spring 2022 engg 2440 discrete mathematics for engineers fall 2021
|
